• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.43 no.5 s.311
• /
• pp.38-47
• /
• 2006

Conventional classification method uses a single classifier based on shape or motion feature. However this method exhibits a weakness if naively used since the classification performance is highly sensitive to the accuracy of moving region to be detected. The detection accuracy, in turn, depends on the condition of the image background. In this paper, we propose to resolve the drawback and thus strengthen the classification reliability by employing a Bayesian decision fusion and by optimally combining the decisions of three classifiers. The first classifier is based on shape information obtained from Fourier descriptors while the second is based on the shape information obtained from image gradients. The third classifier uses motion information. Our experimental results on the classification Performance of human and vehicle with a static camera in various directions confirm a significant improvement and indicate the superiority of the proposed decision fusion method compared to the conventional Majority Voting and Weight Average Score approaches.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.22 no.3
• /
• pp.362-370
• /
• 2011

This paper presents a K-band radar system installed on the ground moving vehicle to detect and track a high-speed target. The presented radar is separated into three search regions to satisfy a wide area detection and a limitation of the installing space of the radar, and each region performs detecting the target independently and tracking the detected target automatically. The presented radar radiating K-band FMCW waveform acquires range and velocity information of the target at the every dwell and receiving antenna of the radar is applied the multiple baseline interferometer to extract the precise angle information of the target. 3-dimensional tracking accuracy of the radar is 0.25 m RMSE measured actually through a fire experiment of an imitation target.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• v.1
• /
• pp.41-46
• /
• 2006

This paper describes a marine watch system on a ship, which is aided by an image processing method. The system detects other ships through a navigational image sequence to prevent oversights, and it measures their bearings to maintain their movements. The proposed method is described, the detection techniques and measurement of bearings techniques are derived, and the results have been reported. The image is divided into small regions on the basis of the brightness value and then labeled. Each region is considered as a template. A template is assumed to be a ship. Then, the template is compared with frames in the original image after a selected time. A moving vector of the regions is calculated using an Excel table. Ships are detected using the characteristics of the moving vector. The video camera captures 30 frames per second. We segmented one frame into approximately 5000 regions; from these, approximately 100 regions are presumed to be ships and considered to be templates. Each template was compared with frames captured at 0.33 s or 0.66 s. In order to improve the accuracy, this interval was changed on the basis of the magnification of the video camera. Ships’ bearings also need to be determined. The proposed method can measure the ships’ bearings on the basis of three parameters: (1) the course of the own ship, (2) arrangement between the camera and hull, and (3) coordinates of the ships detected from the image. The course of the own ship can be obtained by using a gyrocompass. The camera axis is calibrated along a particular direction using a stable position on a bridge. The field of view of the video camera is measured from the size of a known structure on the hull in the image. Thus, ships’ bearings can be calculated using these parameters.

• The KIPS Transactions:PartD
• /
• v.9D no.5
• /
• pp.915-924
• /
• 2002

Conventional Systems for parcel sorting consist of two sequences as loading the parcel into conveyor belt system and post-code input. Using bar code information, the parcels to be recorded and managed are recognized. This paper describes a 32 $\times$ 32 sized mini-block inspection to extract bar code Region of Interest (ROI) from the line Charged Coupled Device (CCD) camera capturing image of moving parcel at 2m/sec speed. Firstly, the Min-Max distribution of the mini-block has been applied to discard the background of parcel and region of conveying belts from the image. Secondly, the diagonal inspection has been used for the extraction of letters and bar code region. Five horizontal line scanning detects the number of edges and sizes and ROI has been acquired from the detection. The wrong detected area has been deleted by the comparison of group size from labeling processes. To correct excluded bar code region in mini-block processes and for analysis of bar code information, the extracted ROI 8 boundary points and decline distribution have been used with central axis line adjustment. The ROI extraction and central axis creation have become enable within 60～80msec, and the accuracy has been accomplished over 99.44 percentage.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2001.11b
• /
• pp.149-154
• /
• 2001

멀티미디어 정보표현 기술인 MPEG-7 표준이 빠른 속도의 진전을 보임에 따라 이를 활용한 검색 기술 개발도 활발히 진행 중에 있다 방대한 량의 동영상 내용 검색 기술 연구에 있어서 우선적으로 고려되어야 할 부분이 내용이 연속되는 프레임들의 분류이다. 이를 위해서는 물리적인 장면전환이 이루어지는 부분에 대한 실시간 자동 cut detection 기술 및 이 컷 프레임 영상에 대한 내용 기술을 자동적으로 수행할 필요성이 있다. 각 컷 프레임의 자동 내용 기술의 전처리로써 본 논문에서는 장면전환이 생기는 프레임의 영상의 어떠한 정보도 사전 정보로 취하지 않고 사용자의 개입이 없는 상황에서 영상의 컬러 특성 및 에지 정보만을 가지고 shape 영역 segmentation을 자동으로 실행하는 방법을 제안한다. 제안한 방법의 성능은 segmentation된 영상과 원 영상과의 영역비교를 통한 유사도에 의해 평가하며, 시뮬레이션 결과에서 제안한 알고리즘은 평균 90%이상의 영역 분할이 정확하게 됨을 알 수 있었고, 컬러의 구분이 명확하지 않은 자연영상에서도 robust한 segmentation 결과를 나타냄을 본 연구를 통하여 알 수 있었다.

• The KIPS Transactions:PartB
• /
• v.10B no.4
• /
• pp.359-366
• /
• 2003

We propose a real-time stereoscopic image conversion method that can generate stereoscopic image with different perspective depth using motion parallax from 2-D image and offer realistic 3-D effect regardless of the direction and velocity of the moving object in the 2-D image. The stereoscopic image is generated by computing the motion parallax between adjacent two 2-D images using the proposed method for motion detection, region segmentation and depth map generation. The proposed method is suitable for real-time stereoscopic conversion processing on various image formats. It has been verified the proposed method by comparing between the stereoscopic image of the proposed method and that of MTD.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.28B no.7
• /
• pp.566-577
• /
• 1991

In this paper, the method of image segmentation based on a pyramid of reduced resolution versions of the input input image is persented. In a pyramid structure, two regions (a given pixel and its mother pixels) are compared by the proposed inverse-mother-son variance ratio (IMSVR) method for the detection of an optinal object pixel and are determined whether they are similar enough to be viewed as one region or disparate to be viewed as ditinct regions By the proposed method, an l`timal object pixel has been setectedat some level, it is necessary to retrieve its boundary precisely. Moving down the pyramid to levels of higher resolution is requires. In this paper, the top-sown pyramid traversing algorithm for an image segmentation using a pyrmid structure is presented. Using the computer simulation, the results by the proposed statistical method and object traversing method are investigated for the binary image and the real image at the results of computer simulation, the proposed method of image segmentation based on a pyramid structure seem to have useful properties and deserve consideration as a possible alternative to existing methods of omage segmentation. The computation for the proposed method is required 0 (log n), for an TEX>$n{\times}n$ input image.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.7 no.6
• /
• pp.1304-1311
• /
• 2003

Target tracking in a real world situation is difficult problem because of continuous variations in images, huge amounts of data, and high processing speed demands. The problem becomes even harder in the case of sea background. This paper presents an initial study of neural network based method for target detection and tracking in cluttering environment. The approach uses a combination of differential motion analysis, Kohonen self-organizing network and region growing method. The network is capable of detecting the mass-centers of moving objects within one frame. The history of neurons positions in the sequential frames approximates the traces of the targets. The experiments done with the network in simulated environment showed promising results.

• Journal of Korea Multimedia Society
• /
• v.21 no.9
• /
• pp.1044-1051
• /
• 2018

In this paper, we propose a new method to improve low light image. In order to improve the image quality of a night image with a moving object as much as the quality of a daytime image, the following tasks were performed. Firstly, we reduce the noisy of the input night image and improve the night image by the tone mapping method. Secondly, we segment the input night image into a foreground with motion and a background without motion. The motion is detected using both the difference between the current frame and the previous frame and the difference between the current frame and the night background image. The background region of the night image takes pixels from corresponding positions in the daytime image. The foreground regions of the night image take the pixels from the corresponding positions of the image which is improved by the tone mapping method. Experimental results show that the proposed method can improve the visual quality more clearly than the existing methods.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.9 no.3
• /
• pp.166-171
• /
• 2009

In recent years, video detection systems have been implemented in various infrastructures such as airport, public transportation, power generation system, water dam and so on. Recognizing moving objects in video sequence is an important problem in computer vision, with applications in several fields, such as video surveillance and target tracking. Segmentation and tracking of multiple vehicles in crowded situations is made difficult by inter-object occlusion. In the system described in this paper, the mean shift algorithm is firstly used to filter and segment a color vehicle image in order to get candidate regions. These candidate regions are then analyzed and classified in order to decide whether a candidate region contains a license plate or not. And then some characters in the license plate is recognized by using the fuzzy ARTMAP neural network, which is a relatively new architecture of the neural network family and has the capability to learn incrementally unlike the conventional BP network. We finally design a license plate recognition system using the mean shift algorithm and fuzzy ARTMAP neural network and show its performance via some computer simulations.